Extracting Semantic Knowledge from GANs with Unsupervised Learning

• URL: http://arxiv.org/abs/2211.16710v1
• Date: Wed, 30 Nov 2022 03:18:16 GMT
• Title: Extracting Semantic Knowledge from GANs with Unsupervised Learning
• Authors: Jianjin Xu, Zhaoxiang Zhang, Xiaolin Hu
• Abstract summary: Generative Adversarial Networks (GANs) encode semantics in feature maps in a linearly separable form. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN's features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects.
• Score: 65.32631025780631
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recently, unsupervised learning has made impressive progress on various tasks. Despite the dominance of discriminative models, increasing attention is drawn to representations learned by generative models and in particular, Generative Adversarial Networks (GANs). Previous works on the interpretation of GANs reveal that GANs encode semantics in feature maps in a linearly separable form. In this work, we further find that GAN's features can be well clustered with the linear separability assumption. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN's features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects, e.g., car, portrait, animals, and so on. With KLiSH, we can sample images from GANs along with their segmentation masks and synthesize paired image-segmentation datasets. Using the synthesized datasets, we enable two downstream applications. First, we train semantic segmentation networks on these datasets and test them on real images, realizing unsupervised semantic segmentation. Second, we train image-to-image translation networks on the synthesized datasets, enabling semantic-conditional image synthesis without human annotations.

Related papers

• Linking in Style: Understanding learned features in deep learning models [0.0]
  Convolutional neural networks (CNNs) learn abstract features to perform object classification. We propose an automatic method to visualize and systematically analyze learned features in CNNs.
  arXiv  Detail & Related papers  (2024-09-25T12:28:48Z)
• DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models [61.906934570771256]
  We present a generic dataset generation model that can produce diverse synthetic images and perception annotations. Our method builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation. We show that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module.
  arXiv  Detail & Related papers  (2023-08-11T14:38:11Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization [112.68171734288237]
  We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
  arXiv  Detail & Related papers  (2021-04-12T21:41:25Z)
• Linear Semantics in Generative Adversarial Networks [26.123252503846942]
  We aim to better understand the semantic representation of GANs, and enable semantic control in GAN's generation process. We find that a well-trained GAN encodes image semantics in its internal feature maps in a surprisingly simple way. We propose two few-shot image editing approaches, namely Semantic-Conditional Sampling and Semantic Image Editing.
  arXiv  Detail & Related papers  (2021-04-01T14:18:48Z)
• Repurposing GANs for One-shot Semantic Part Segmentation [1.6543719822033436]
  We propose a simple and effective approach based on GANs for semantic part segmentation. Our key idea is to leverage a trained GAN to extract pixel-wise representation from the input image and use it as feature vectors for a segmentation network. Our experiments demonstrate that GANs representation is "readily discriminative" and produces surprisingly good results.
  arXiv  Detail & Related papers  (2021-03-07T15:40:47Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• Scribble-Supervised Semantic Segmentation by Random Walk on Neural Representation and Self-Supervision on Neural Eigenspace [10.603823180750446]
  This work aims to achieve semantic segmentation supervised by scribble label directly without auxiliary information and other intermediate manipulation. We impose diffusion on neural representation by random walk and consistency on neural eigenspace by self-supervision. The results demonstrate the superiority of the proposed method and are even comparable to some full-label supervised ones.
  arXiv  Detail & Related papers  (2020-11-11T08:22:25Z)
• Pairwise Relation Learning for Semi-supervised Gland Segmentation [90.45303394358493]
  We propose a pairwise relation-based semi-supervised (PRS2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net) We evaluate our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset.
  arXiv  Detail & Related papers  (2020-08-06T15:02:38Z)
• OpenGAN: Open Set Generative Adversarial Networks [16.02382549750862]
  We propose an open set GAN architecture (OpenGAN) that is conditioned per-input sample with a feature embedding drawn from a metric space. We are able to generate samples that are semantically similar to a given source image. We show that performance can be significantly improved by augmenting the training data with OpenGAN samples on classes that are outside of the GAN training distribution.
  arXiv  Detail & Related papers  (2020-03-18T07:24:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.